yzma

yzma 1.30 is over 2.6 times faster at embeddings than Ollama or @docker.com Model Runner! New benchmarks here: yzma.ai/docs/referen... #llamacpp #golang #localAI #ollama #dmr

yzma v1.30 is out with @hf.co llama.cpp v0.7.0 support! More System One decision models, and decision heads running right in your browser. You can go get it right now! github.com/hybridgroup/yzma #golang #llamacpp #yzma #tinygo #systemOne

Things are getting serious, by which we mean you can now play Pac-Man with Jeyzma. See browser AI in real-time action! jeyzma.com/plays/pacman/

Jeyzma is like @typesafeai.bsky.social minus $870 million plus @golang.org & @tinygo.org & @hf.co llama.cpp Go make a decision! Already available right now in your browser. jeyzma.com #jev #decisionAI #browserAI #llamacpp #systemOne

Jeyzma also keeping "browser AI" hot, updated with new models Julia-1 & Laya. Plus the latest high-performance WebGPU builds! Decision support completely local all written in @golang.org with @tinygo.org jeyzma.com #golang #tinygo #localAI #browserAI

yzma 1.29 is out! Run high performance local AI models from @golang.org without CGo. Support for the new @hf.co llama.cpp v0.6.0, typed decisions w/ System One models, auto-threading, new extended batch API, & much more! Go get it right now! yzma.ai #golang #llamacpp #gguf #tinygo #localAI

@squillace.bsky.social did you see my recent jeyzma.com yet?

Training for our next show in Japan has our fans whirring...

Announcing Jeyzma: Jev in your browser written in @golang.org with yzma and WebAssembly. Ask a System One model a typed question and get a decision. No server, no API key, no data leaves your machine. WebGPU acceleration too! jeyzma.com #jev #golang #webassembly #wasm #tinygo #webgpu

Need to make a decision? Try Jeyzma! Like Jev in your browser written in Go with WebGPU support. jeyzma.com #golang #jev #tinygo #systemOne #yzma #wasm #webGPU

In two weeks, we will record "Talking Heads From The Year 2053 - Episode Three" in Tokyo, Japan at @tinygo.org Conf! 2週間後、日本の東京で開催されるTinyGo Confにて、『Talking Heads From The Year 2053 - Episode Three』の収録を行います！ conf.tinygo-keeb.org/2026/

llama.cpp + Go でモデルを読んでローカルLLMできる yzma の playground がリリースされてる。 TinyGo で wasm ビルドされてブラウザで動いてる。さらには WebGPU も使えるのでいい感じ。試しに Qwen3.5-2B-UD-Q2_K_XL.gguf で試したけど素直に動く。 #golang #wasm #tinygo yzma.ai/try/

Models in your browser got a big upgrade with yzma 1.28. Our WebAssembly interface now covers 170 functions from @hf.co llama.cpp! You get every sampler, logits, model metadata, performance counters, saved context state in memory, & WebGPU Try it: yzma.ai/try #golang #wasm #tinygo #webgpu

Just over 2 weeks until TinyGo Conf in Tokyo! 東京でのTinyGo Confまで、あと2週間余りです！ conf.tinygo-keeb.org/2026/ #tinygo #tinygoconf #golang #embedded #wasm #tinygoKeeb

yzma 1.28 is out! Run local AI models from Go with no CGo. Support for the new @hf.co llama.cpp v0.5.0, OpenVINO, autoselect CUDA, updated benchmarks, more WASM support. Go get it right now! yzma.ai #golang #llamacpp #sovereignAI #localAI

We just released yzma 1.27 to match the new @hf.co llama.cpp 0.4.1 Go get it! github.com/hybridgroup/...

Very cool, our latest release is in the new Golang Weekly newsletter! 🤖 yzma 1.26: Local LLM Inference from Go, Now in the Browser golangweekly.com/issues/617 #golang #llamacpp #tinygo #wasm #webgpu

"Talking Heads From The Year 2053" runs on hardware partly provided by @officialarduino.bsky.social Thank you!

Check out the new #Yzma website and try Yzma in the browser while you are there! #golang yzma.ai

Hello #webAssembly people! How about 100% local inference in your browser with #WebGPU using the new @yzma.ai with @golang.org @tinygo.org @hf.co #llama Try it right now! yzma.ai/try/

I made a hands-on workshop for Go developers to play with local LLMs using yzma! github.com/mi-bear/yzma... (Note: it’s in Japanese only) Thinking of trying this out at a Women Who Go Tokyo meetup.

yzma v1.26 is here and it is the big one: local inference in the browser! Write @golang.org, compile with @tinygo.org, run GGUF models 100% locally on WebAssembly. Uses WebGPU/CPU Plus @hf.co llama.cpp v0.4.0 support. Go get it! github.com/hybridgroup/yzma #golang #tinygo #wasm #webgpu #yzma

100% local chat with a GGUF model in your browser using WebAssembly. Written in @golang.org compiled with @tinygo.org. Runs in @developer.chrome.com / @firefox.com, supports WebGPU when available. Try it! hybridgroup.github.io/yzma-wasm-ex... #golang #wasm #llama #tinygo #yzma #gguf #webgpu

100% local chat with a model in your browser using WebAssembly written in TinyGo hybridgroup.github.io/yzma-wasm-ex... #llama #llm #wasm #tinygo #golang

The AI takeover continues in Episode Two. In this scene special guest star @boursiquot.com asks Phineas a question with hilarious results. See the only show with robot actors run on @officialarduino.bsky.social UNQ Q boards & @golang.org / @tinygo.org code on @github.com youtu.be/Pny5TFP2r3U

Episode Two is out! The AI takeover continues with @deadprogram.com + @boursiquot.com @filippo.abyssdomain.expert @doniacld.bsky.social +Patricio Whittingslow at @gophercon.com The only show w/ actors running on @officialarduino.bsky.social UNO Q, @golang.org & @tinygo.org youtu.be/Pny5TFP2r3U

Talking Heads From The Year 2053 - Episode Two comes out tomorrow! 13:00 UTC (06:00 PT / 07:00 MT / 09:00 ET / 15:00 CET / 21:00 ST/CST) We have many surprises for you, including some special guest stars... www.youtube.com/@TalkingHead... #gophercon #arduino #golang #tinygo #th2053

First up @goinggo.net lightning talk about kronkai.com here at @gophercon.com #gophercon #golang #llm #llamacpp

Shooting Episode Two right now here at @gophercon.com #th2053

Here we go, the journey to @gophercon.com has begun! #gophercon #golang #tinygo

"How exactly do you plan to dismantle the servers of your rival AIs?" Find out on "Talking Heads From The Year 2053" our robotic comedy improv show that combines absurdist humor with cutting edge technology. www.youtube.com/watch?v=aicf... #robots #tech #BigTech #AI #ArtificialIntelligence

"What happened to the original human executives who created you?" Find out on Talking Heads From The Year 2053 - Episode One available now! youtu.be/aicfLYrRuUw #llm #robots #robotOverlords #tech #BigTech #AI #ArtificialIntelligence

3 talking robot heads & one human with a tinfoil helmet, communicating from the future. Part biting social commentary, part technology demonstration, all recorded live. Go watch Episode One right now! www.youtube.com/watch?v=aicf... #ai #llm #robots #robotTakeover #robotActors

yzma v1.18 is out, with the freshest of @hf.co llama.cpp multimedia features including video input, batching, & more. Go get it while it's hot! github.com/hybridgroup/... #golang #llamacpp #inference #gguf #yzma

Did you know that Talking Heads From The Year 2053 runs on @officialarduino.bsky.social The code and models for each of the actors run entirely on the Arduino UNO Q no cloud! Check out Episode One here: youtu.be/aicfLYrRuUw #th2053 #golang #arduino #yzma #llamacpp

"Talking Heads From The Year 2053 - Episode One" is out! At last, Episode One of the show that answers your most important questions about the future, from the future. Go watch it right now! youtu.be/aicfLYrRuUw #th2053 #golang #arduino

"Episode One" is in the can, thanks again to everyone at @gopherconeu.bsky.social Look for it online next week!

It was another excellent @gopherconeu.bsky.social thank you very much to the speakers, staff, sponsors, and especially everyone who attended and was a part of @talkingheads2053.com Episode One!

Getting ready to record @talkingheads2053.com Episode One here at @gopherconeu.bsky.social #th2053 #gopherconEU #golang #tinygo

Cyborgs never stop, so here is yzma 1.16 to keep up with the rapid pace of the @hf.co llama.cpp team. Go get it, you'll need it! github.com/hybridgroup/...

"Free Yourself From The Copilot Tax" The hardworking @goinggo.net & friends have been building all the high-level tooling/APIs for local inference on top of @yzma.ai Kronk looks great & works very well. Perfect timing to take control of your destiny! www.kronkai.com/blog/free-yo...

Did you know that each of the "Talking Heads From The Year 2053" runs on its own @officialarduino.bsky.social UNO Q board? More on "How To Get A Head" coming soon... #golang #arduino #tinygo #th2053

The live recording for "Talking Heads From The Year 2053 - Episode One" is in less than 2 weeks at @gopherconeu.bsky.social and we have a lot to say... Get ready, humans of 2026! www.gophercon.eu #golang #tinygo #gopherconEU #arduino #th2053 #talkingHeads2053 #futureAI

GitHub Copilot’s switch to token-based billing is turning $29 subscriptions into $750 bills overnight. And developers are right to be furious. In @goinggo.net latest post on Kronk AI: Free Yourself from the Copilot Tax → www.kronkai.com/blog/free-yo...

GitHub Copilot's switch to token-based billing is turning $29 subscriptions into $750 bills overnight, and developers are right to be furious. Install #Kronk, point VS Code Chat at it, and get back to writing code. www.kronkai.com/blog/free-yo...

yzma 1.15 is out, needed for both breaking changes to llama.cpp & also for our new, more robust library updater. Go get it! github.com/hybridgroup/... #golang #llamacpp #localAI #yourIntelligence

Physical AI running locally on @officialarduino.bsky.social UNO Q like you've never seen before (and won't until 2053) "Talking Heads From The Year 2053 - Episode Zero" is available now! www.youtube.com/watch?v=woky... #th2053 #talkingHeads2053 #arduino #golang #tinygo #llm #tlm #robotOverlords

Are we actually the first show that has a Github repo with the Go source code for the actors and the whole production pipeline? github.com/talkingheads... #th2053 #talkingheads2053 #golang #tinygo #arduino #robots

Episode Zero is available now! youtu.be/wokyfBA7lbY?...

10 minutes to Go! www.youtube.com/watch?v=woky...